# Building an AI Agent Supervisor: Series Index


This series documents the architecture, decisions, and lessons from building Batty — a Rust CLI that supervises teams of AI coding agents in tmux.

Each post covers a specific subsystem or challenge. Start anywhere — they're designed to be useful independently.

## The Architecture

1. **[How I Run a Team of AI Coding Agents in Parallel](https://dev.to/battyterm/how-i-run-a-team-of-ai-coding-agents-in-parallel)** — The problem and the solution. Why running multiple agents on the same repo breaks without coordination.

2. **[Building a tmux-native agent supervisor in Rust](https://dev.to/battyterm/building-a-tmux-native-agent-supervisor-in-rust-5hek)** — Deep dive into the Rust implementation. Crate choices, architecture decisions, what I'd do differently.

3. **[Why I Chose a Synchronous Poll Loop Over Async](https://dev.to/battyterm/why-i-chose-a-synchronous-poll-loop-over-async-for-my-rust-daemon-1416)** — I ripped out tokio after two weeks. Here's why sleep(5) was the right call.

4. **[How tmux Became the Runtime](https://dev.to/battyterm/how-tmux-became-the-runtime-for-ai-agent-teams-gmi)** — Why tmux, not Docker or a custom TUI, is the perfect agent runtime.

## The Patterns

5. **[Git Worktrees for AI Agent Isolation](https://dev.to/battyterm/how-to-use-git-worktrees-to-run-multiple-ai-agents-on-the-same-repo-1on8)** — Step-by-step tutorial for parallel agent work without file conflicts.

6. **[The Case for Markdown as Your Agent's Task Format](https://dev.to/battyterm/the-case-for-markdown-as-your-agents-task-format-6mp)** — Why Markdown beats JSON for agent task management.

7. **[Context Rotation: When Agents Run Out of Memory](https://dev.to/battyterm/context-rotation-for-ai-coding-agents-what-happens-when-they-run-out-of-memory-17f6)** — Detection, rotation patterns, and scoping tasks to fit context windows.

8. **[Your AI Agent Says Done — How Do You Know?](https://dev.to/battyterm/your-ai-agent-says-done-how-do-you-know-it-actually-worked-3mfc)** — Test gating as the quality gate. Exit code 0 means done.

## The Practice

9. **[5 Lessons from Running AI Agents in Parallel](https://dev.to/battyterm/5-lessons-from-running-ai-coding-agents-in-parallel-53on)** — Task decomposition, test gating, worktree isolation, supervision vs autonomy.

10. **[From Solo Agent to Agent Team: A Migration Guide](https://dev.to/battyterm/from-solo-agent-to-agent-team-a-migration-guide-474c)** — Progressive 6-stage path from one agent to full automation.

11. **[The Real Cost of Running 5 Agents in Parallel](https://dev.to/battyterm/the-real-cost-of-running-5-ai-coding-agents-in-parallel-1lo)** — Token math, cost reduction tactics. 1.5-2x not 5x.

12. **[Choosing an AI Agent Orchestrator in 2026](https://dev.to/battyterm/choosing-an-ai-agent-orchestrator-in-2026-a-practical-comparison-i0k)** — Honest comparison: Batty vs vibe-kanban vs CrewAI vs AutoGen vs tmux scripts.


**The tool:** [github.com/battysh/batty](https://github.com/battysh/batty) — open source, MIT licensed, built in Rust.